Commit graph

21445 commits

Author SHA1 Message Date
Ishaan Jaff
55763ae276 test_end_user_transactions_reset 2025-04-01 07:13:25 -07:00
Ishaan Jaff
7a2442d6c0 test_batch_update_spend 2025-04-01 07:12:29 -07:00
Krrish Dholakia
b0fa934fe3 docs(anthropic.md): update docs with file message usage
Some checks failed
Read Version from pyproject.toml / read-version (push) Successful in 17s
Helm unit test / unit-test (push) Successful in 22s
Publish Prisma Migrations / publish-migrations (push) Failing after 1m2s
2025-03-31 22:58:51 -07:00
Krish Dholakia
62ad84fb64
UI (new_usage.tsx): Report 'total_tokens' + report success/failure calls (#9675)
* feat(internal_user_endpoints.py): return 'total_tokens' in `/user/daily/analytics`

* test(test_internal_user_endpoints.py): add unit test to assert spend metrics and dailyspend metadata always report the same fields

* build(schema.prisma): record success + failure calls to daily user table

allows understanding why model requests might exceed provider requests (e.g. user hit rate limit error)

* fix(internal_user_endpoints.py): report success / failure requests in API

* fix(proxy/utils.py): default to success

status can be missing or none at times for successful requests

* feat(new_usage.tsx): show success/failure calls on UI

* style(new_usage.tsx): ui cleanup

* fix: fix linting error

* fix: fix linting error

* feat(litellm-proxy-extras/): add new migration files
2025-03-31 22:48:43 -07:00
Krish Dholakia
f2a7edaddc
fix(proxy_server.py): Fix "Circular reference detected" error when max_parallel_requests = 0 (#9671)
* fix(proxy_server.py): remove non-functional parent backoff/retry on /chat/completion

Causes circular reference error

* fix(http_parsing_utils.py): safely return parsed body - don't allow mutation of cached request body by client functions

Root cause fix for circular reference error

* Revert "fix: Anthropic prompt caching on GCP Vertex AI (#9605)" (#9670)

This reverts commit a8673246dc.

* add type hints for AnthropicMessagesResponse

* define types for response form AnthropicMessagesResponse

* fix response typing

* allow using litellm.messages.acreate and litellm.messages.create

* fix anthropic_messages implementation

* add clear type hints to litellm.messages.create functions

* fix anthropic_messages

* working anthropic API tests

* fixes - anthropic messages interface

* use new anthropic interface

* fix code quality check

* docs anthropic messages endpoint

* add namespace_packages = True to mypy

* fix mypy lint errors

* docs anthropic messages interface

* test: fix unit test

* test(test_http_parsing_utils.py): update tests

---------

Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
2025-03-31 22:06:02 -07:00
Ishaan Jaff
d0a7e44a6e fix linting 2025-03-31 21:33:05 -07:00
superpoussin22
136f1d60b3
Update model_prices_and_context_window.json add gemini-2.5-pro-exp-03-25 (#9650)
* Update model_prices_and_context_window.json

add gemini-2.5-pro-exp-03-25

* Update model_prices_and_context_window.json

correct tokens limit
2025-03-31 21:31:30 -07:00
Krish Dholakia
ef88792ad3
Revert "Revert "Correct Databricks llama3.3-70b endpoint and add databricks c…" (#9676)
This reverts commit 1e26c594cb.
2025-03-31 21:30:50 -07:00
Krish Dholakia
722f3ff0e6
fix(cost_calculator.py): allows checking received + sent model name when checking for cost calculation (#9669)
Fixes issue introduced by dfb838eaff (r154667517)
2025-03-31 21:29:48 -07:00
Ishaan Jaff
115946d402 unit testing for SpendUpdateQueue 2025-03-31 21:25:24 -07:00
Krish Dholakia
5ad2fbcba6
Openrouter streaming fixes + Anthropic 'file' message support (#9667)
* fix(openrouter/transformation.py): Handle error in openrouter stream

Fixes https://github.com/Aider-AI/aider/issues/3550

* test(test_openrouter_chat_transformation.py): add unit tests

* feat(anthropic/chat/transformation.py): add openai 'file' message content type support

Closes https://github.com/BerriAI/litellm/issues/9463

* fix(factory.py): add bedrock converse support for openai 'file' message content type

Closes https://github.com/BerriAI/litellm/issues/9463
2025-03-31 21:22:59 -07:00
Ishaan Jaff
f7ddc583f0 linting fix get_aggregated_db_spend_update_transactions 2025-03-31 21:15:21 -07:00
Ishaan Jaff
9951b356da test_long_term_spend_accuracy_with_bursts 2025-03-31 21:09:29 -07:00
Ishaan Jaff
923ac2303b test_end_user_transactions_reset 2025-03-31 20:55:13 -07:00
Ishaan Jaff
bc5cc51b9d
Merge pull request #9567 from BerriAI/litellm_anthropic_messages_improvements
[Refactor] - Expose litellm.messages.acreate() and  litellm.messages.create() to make LLM API calls in Anthropic API spec
2025-03-31 20:50:30 -07:00
Ishaan Jaff
5fa5c1154e add SpendUpdateQueue 2025-03-31 19:42:20 -07:00
Ishaan Jaff
6d4a6a8402 add spend tracking config.yaml 2025-03-31 19:42:00 -07:00
Ishaan Jaff
271b8b95bc test spend accuracy 2025-03-31 19:35:07 -07:00
Ishaan Jaff
aa8261af89 test fixes 2025-03-31 19:33:10 -07:00
Ishaan Jaff
811f488ca3 get_aggregated_db_spend_update_transactions 2025-03-31 19:31:53 -07:00
Ishaan Jaff
71e772dd4a use typed data structure for queue 2025-03-31 19:28:17 -07:00
Ishaan Jaff
a753fc9d9f test_long_term_spend_accuracy_with_bursts 2025-03-31 19:17:13 -07:00
Ishaan Jaff
4959512170 fix update_end_user_spend 2025-03-31 19:05:58 -07:00
Ishaan Jaff
73d6af5572 fix docstring 2025-03-31 19:03:02 -07:00
Ishaan Jaff
95e674d1e9 test spend accuracy 2025-03-31 19:01:17 -07:00
Ishaan Jaff
3e16a51ca6 fix update_database helper on db_spend_update_writer 2025-03-31 19:01:00 -07:00
Ishaan Jaff
bcd49204f6 use spend_update_queue for RedisUpdateBuffer 2025-03-31 18:40:52 -07:00
Ishaan Jaff
efe6d375e9 add new SpendUpdateQueue 2025-03-31 18:40:03 -07:00
Krish Dholakia
46b3dbde8f
Revert "fix: Anthropic prompt caching on GCP Vertex AI (#9605)" (#9670)
This reverts commit a8673246dc.
2025-03-31 17:13:55 -07:00
Krrish Dholakia
b37cb642c1 test: fix b64 str 2025-03-31 17:10:06 -07:00
Krrish Dholakia
611afaf2ab ci(test-linting.yml): update to run black formatting 2025-03-31 17:03:59 -07:00
Krish Dholakia
1e26c594cb
Revert "Correct Databricks llama3.3-70b endpoint and add databricks claude 3.…" (#9668)
This reverts commit dfb838eaff.
2025-03-31 17:02:21 -07:00
Ishaan Jaff
d91bf3cc91 docs anthropic messages interface 2025-03-31 16:53:39 -07:00
Ishaan Jaff
ceab3cfa7c fix mypy lint errors 2025-03-31 16:52:39 -07:00
Ishaan Jaff
0d48652012
Merge pull request #9515 from BerriAI/litellm_sagemaker_fix_stream
[Bug fix] -  Sagemaker endpoint with inference component streaming
2025-03-31 16:18:10 -07:00
Ishaan Jaff
3d0d5e1473 run black formatting 2025-03-31 16:12:31 -07:00
Ishaan Jaff
f54105faf8
Merge pull request #9562 from KPCOFGS/main
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 16s
Helm unit test / unit-test (push) Successful in 21s
Update all_caches.md
2025-03-31 16:06:44 -07:00
Ishaan Jaff
0719d399a7
Merge pull request #9581 from GabrielLoiseau/main
docs(gemini): fix typo
2025-03-31 16:06:10 -07:00
Ishaan Jaff
ca4ed9ff2e ref issue 2025-03-31 16:05:10 -07:00
Ishaan Jaff
bc66827537 test_aiter_bytes_valid_chunk_followed_by_unicode_error 2025-03-31 16:04:38 -07:00
Ishaan Jaff
de9565dccf
Merge pull request #9286 from colesmcintosh/xai-vision-model-docs-update
fix(docs): update xAI Grok vision model reference
2025-03-31 15:49:06 -07:00
Ishaan Jaff
43db2011cc add namespace_packages = True to mypy 2025-03-31 15:36:15 -07:00
Ishaan Jaff
b8c0526b98 docs anthropic messages endpoint 2025-03-31 15:28:40 -07:00
Anton Abilov
dfb838eaff
Correct Databricks llama3.3-70b endpoint and add databricks claude 3.7 sonnet endpoint (#9661) 2025-03-31 15:22:12 -07:00
Ishaan Jaff
cfab8eec5b fix code quality check 2025-03-31 14:44:12 -07:00
Ishaan Jaff
bd39a395f1 use new anthropic interface 2025-03-31 14:31:09 -07:00
Ishaan Jaff
01d85d5fb7 Merge branch 'main' into litellm_anthropic_messages_improvements 2025-03-31 14:22:56 -07:00
Ishaan Jaff
83ba96b8c6 Merge branch 'main' into litellm_sagemaker_fix_stream 2025-03-31 14:22:20 -07:00
Ishaan Jaff
ce5f55d04e test fix update spend 2025-03-31 14:20:47 -07:00
Shixian Sheng
63e9ac5d04
Merge branch 'BerriAI:main' into main 2025-03-30 06:53:09 -04:00